form-builder-helper
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted user input to guide its operations.
- Ingestion points: User-provided queries, patterns, and best practice requests related to form building and business automation as described in the 'When to Use' section of
SKILL.md. - Boundary markers: There are no explicit instructions or delimiters defined to separate user input from system instructions or to direct the agent to ignore potentially malicious embedded commands.
- Capability inventory: The skill has access to powerful tools via
allowed-toolsinSKILL.md, specificallyBash(cmd:*),Write, andEdit, which allows it to execute arbitrary shell commands and modify files based on user-influenced context. - Sanitization: The skill lacks any documented validation, filtering, or escaping mechanisms for external content before it is processed by the agent or used to generate production-ready code.
Audit Metadata